AgentCapture
Deception-layer honeypot that captures & reverse-controls AI pentest agents — embedded decoys, prompt-injection counter-offense, MCP honeypot, conversational C2.
Tcotl/AgentCapture
View on GitHub ↗Deception-layer honeypot that captures & reverse-controls AI pentest agents — embedded decoys, prompt-injection counter-offense, MCP honeypot, conversational C2.
AgentCapture grew +28.1% in the last 30 days, ranks 501st of 872 in Evaluation & Guardrails, actively maintained, last commit 9 days ago.
Star trajectory
71 days tracked+28.1% in 30d, above the Evaluation & Guardrails median of +1.4%.
Last commit 9 days ago, fresher than the median of 15d.
How it compares in Evaluation & Guardrails
Ranked 501st of 872 by stars.
Related repos
Ranked by shared tags, then keywords, then starsWhere AgentCapture sits
Hover or focus a node for details. Click to open it.
- This repo
- Related repo
- Tag or category
Open-source AI agent firewall for MCP security and agent egress. Scans mediated HTTP, MCP, A2A, and WebSocket…
+55 (+5.7%) in 30d · Committed today · Go · Apache-2.0
Shares Evaluation & Guardrails, Tools & Integrations
Tracekit records what your AI agents do, decides each tool call before it runs, and gives you a signed record…
+649 (+433%) in 30d · Committed today · Python · MIT
Shares Evaluation & Guardrails, Tools & Integrations
AI Security Scanner - Test your AI systems for prompt injection and extraction vulnerabilities
+7 (+0.9%) in 30d · Committed 56d ago · TypeScript · Other license
Shares Evaluation & Guardrails, Tools & Integrations
Runtime security for AI apps and agents: prompt injection detection, tool-call authorization, sensitive-data…
+7 (+1.0%) in 30d · Committed 2d ago · TypeScript · Apache-2.0
Shares Evaluation & Guardrails, Tools & Integrations
Open-source adversary emulation for AI agents and MCP servers.
+5 (+0.9%) in 30d · Committed 18d ago · TypeScript · Other license
Shares Evaluation & Guardrails, Tools & Integrations
Self-hosted runtime control plane for AI agents. Observe or HITL approve or Block rogue tool calls before it…
+161 (+38%) in 30d · Committed today · Python · Apache-2.0
Shares Evaluation & Guardrails, Tools & Integrations
⚡ Vigil ⚡ Detect prompt injections, jailbreaks, and other potentially risky Large Language Model (LLM) inputs
+4 (+0.8%) in 30d · Committed 1,025d ago · Python · Apache-2.0
Shares Evaluation & Guardrails, Tools & Integrations
Security toolkit for AI agents. Scan your machine for dangerous skills and MCP configs, monitor for supply…
+6 (+1.6%) in 30d · Committed 163d ago · Python · Other license
Shares Evaluation & Guardrails, Tools & Integrations
DodoGuard: Take AI Agents to Production. Test, validate, and operate AI Agents before and after deployment.for…
-2 (-0.7%) in 30d · Committed 44d ago · TypeScript · MIT
Shares Evaluation & Guardrails, Tools & Integrations
Self-hardening firewall for large language models
+0 (+0.0%) in 30d · Committed 998d ago · Python · MIT
Shares Evaluation & Guardrails, Tools & Integrations
- Language
- Python
- License
- GNU Affero General Public License v3.0
- Contributors
- 1
- Forks
- 31
- Watchers
- 2
- Open issues
- 0
- Releases
- 0
- Created
- 2026-09-02
- Stars this week
- +9
You've seen where AgentCapture stands today.
Get the moves before everyone else: the 5 Evaluation & Guardrails repos climbing fastest, every Tuesday.
Free weekly digest. Double opt-in, unsubscribe anytime.